<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Image to Text - Hugging Face Transformers.js</title>
<script type="module">
// Import the library
import { pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.4';
// Make it available globally
window.pipeline = pipeline;
</script>
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.0/dist/css/bootstrap.min.css" rel="stylesheet">
<link rel="stylesheet" href="css/styles.css"></head>
<body>
<div class="container-main">
<!-- Page Header -->
<div class="header">
<div class="header-logo">
<img src="images/logo.png" alt="logo">
</div>
<div class="header-main-text">
<h1>Hugging Face Transformers.js</h1>
</div>
<div class="header-sub-text">
<h3>Free AI Models for JavaScript Web Development</h3>
</div>
</div>
<hr> <!-- Separator -->
<!-- Back to Home button -->
<div class="row mt-5">
<div class="col-md-12 text-center">
<a href="index.html" class="btn btn-outline-secondary"
style="color: #3c650b; border-color: #3c650b;">Back to Main Page</a>
</div>
</div>
<!-- Content -->
<div class="container mt-5">
<!-- Centered Titles -->
<div class="text-center">
<h2>Computer Vision</h2>
<h4>Image to Text</h4>
</div>
<!-- Actual Content of this page -->
<div id="image-to-text-container" class="container mt-4">
<h5>Generate a Caption for an Image w/ Xenova/vit-gpt2-image-captionin:</h5>
<div class="d-flex align-items-center">
<label for="imageToTextURLText" class="mb-0 text-nowrap" style="margin-right: 15px;">Enter
image to Caption URL:</label>
<input type="text" class="form-control flex-grow-1" id="imageToTextURLText"
value="https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg"
placeholder="Enter image" style="margin-right: 15px; margin-left: 15px;">
<button id="ImagetoTextButton" class="btn btn-primary" onclick="captionImage()">Caption</button>
</div>
<div class="mt-4">
<h4>Output:</h4>
<pre id="outputArea"></pre>
</div>
</div>
<hr> <!-- Line Separator -->
<div id="image-to-text-local-container" class="container mt-4">
<h5>Generate a Caption for a Local Image:</h5>
<div class="d-flex align-items-center">
<label for="imagetoTextLocalFile" class="mb-0 text-nowrap"
style="margin-right: 15px;">Select Local Image:</label>
<input type="file" id="imagetoTextLocalFile" accept="image/*" />
<button id="CaptionButtonLocal" class="btn btn-primary"
onclick="captionImageLocal()">Caption</button>
</div>
<div class="mt-4">
<h4>Output:</h4>
<pre id="outputAreaLocal"></pre>
</div>
</div>
<!-- Back to Home button -->
<div class="row mt-5">
<div class="col-md-12 text-center">
<a href="index.html" class="btn btn-outline-secondary"
style="color: #3c650b; border-color: #3c650b;">Back to Main Page</a>
</div>
</div>
</div>
</div>
<script>
let captioner;
// Initialize the sentiment analysis model
async function initializeModel() {
captioner = await pipeline('image-to-text', 'Xenova/vit-gpt2-image-captioning');
}
async function captionImage() {
const textFieldValue = document.getElementById("imageToTextURLText").value.trim();
const result = await captioner(textFieldValue);
document.getElementById("outputArea").innerText = JSON.stringify(result, null, 2);
}
async function captionImageLocal() {
const fileInput = document.getElementById("imagetoTextLocalFile");
const file = fileInput.files[0];
if (!file) {
alert('Please select an image file first.');
return;
}
// Create a Blob URL from the file
const url = URL.createObjectURL(file);
const result = await captioner(url);
document.getElementById("outputAreaLocal").innerText = JSON.stringify(result, null, 2);
}
// Initialize the model after the DOM is completely loaded
window.addEventListener("DOMContentLoaded", initializeModel);
</script>
</body>
</html>